Using A Built-In Sensor Smartphones Can Now Tell When You’re Drunk. According to Inverse, You might have experienced hanging out with your friends at a bar or on a zoom call, tossing back sweet drinks until the room suddenly begins to rock like a hull of a ship. In as much as social lubrication can be a great way to ease from stress or connect with friends, it can also stand a serious personal and public health risk if abused.
However, it’s very important to keep track of your intoxication, although judging by the number of drinks consumed alone is not a perfect way to gauge, because people have different tolerances. Individual breathalyzers or Skin-based detectors are one option, though it may be too stigmatized to use effectively in public for some people. Enter: the smartphone.
Some medical researchers recently investigated how the smartphone’s accelerometer can predict intoxication based on how one walks. In a sample of 17 participants, the researchers were able to predict intoxication with 92% accuracy.
Using A Built-In Sensor Smartphones Can Now Tell When You’re Drunk
In the study, published Tuesday in the journal of studies on alcohol and drugs, researchers from Standford and Pittsburgh University said that their research is complementary to previous studies that identified a varied gait (e.g. Swaying side to side when you walk) as a sign of intoxication. While previous research centered on connections between the number of drinks consumed and a person’s gait. This study zoomed in on blood alcohol concentration and breath alcohol concentration.
Individual tolerance can vary based on a number of variables, for instance, body size, the research team behind this new study believes that blood alcohol concentration(BAC) and breath alcohol concentration(BrAC) may be a more accurate way to measure intoxication.
However, the proof of concept incorporation of smartphone accelerometer data has the potential to be scaled up because of the accessibility of smartphones, the res researchers argue. To get to that future, the team rounded-up a few willing volunteers e get drunk in order to test how well the system works in the wild.
The Alcohol Test
In total, the team recruited 22 people and measured their height and weight to determine what level of alcohol consumption would be necessary to have them intoxicated. 08 BRAC.
Brian Suffoletto, the study’s lead researcher and an associate professor at the Standford University school of medicine’s department of emergency medicine, tells Inverse that one shot of a spirit (vodka) will on average raise a man’s BAC by 0.02 (for men) women’s BAC by 0.03. during the research, Suffoletto was a reseacher at the University of Pittsburgh school of medicine.
“Definitely, for an individual, lots of factors can affect how much a standard drink raises BAC”, according to Suffoletto.
The participants were given alcohol in the form of a vodka Finley and required to drink it within one hour. Then, the participants finished walking trials (10-steps forward and 10-steps backward) each hour for seven- hours with their smartphone strapped to their lower backs. Their BAC and BrAC were measured periodically throughout.
The Alcohol Test Result
The test gave the researchers 17 gaits to analyze (12 male and 5 female) and, subsequently, the team discovered that they were able to accurately predict whether a participant was at or above a 0.08 BrAC based on their gait with 92 % accuracy.
However, the smartphone accelerometer collected multi-axis data on the participants’ movement, and the researchers found that lateral movement (moving back and forth) was a major sign of intoxication.
While the average drinker isn’t likely to strap their phone to the lower backs, Suffoletto tells Inverse that they’re in the process of analyzing how this step-up will work with participants’ phones in their pockets or hands. Suffoletto hypothesizes that phone’s swaying in the participants’ hands may disrupt their prediction, but putting the phone in their pockets should not disrupt their prediction.
Furthermore, to make sure the above approach will work outside the meticulously controlled environment of a lab, Suffoletto says a next step will be testing out the set-up in a more realistic environment (like crowded bar hallways).
Some authors also note in the study that expanding their sample size will be important for showing the generalization of these results. The challenge will now be on how to communicate these intoxication signals to someone effectively, according to Suffoletto.
He continued “ I have spent the past 10+plus years designing and testing communication-based strategies to help people make better choices relating to alcohol consumption.” He added, “ the biggest challenge in my mind is how to get someone who is already impaired with alcohol to respond to supportive messaging.”
So, if things work according to plan, Suffoletto predicts we might seeing apps with this capability in the next year.